A novel approach to diagnosing PCOS through tunica albuginea oculi

Polycystic ovarian syndrome (PCOS) mostly affects women aged fifteen to forty-four years. Using patient tunica albuginea oculi images, we created a deep learning model in this study to predict PCOS. In individuals with PCOS, physiological alterations have been observed in the tunica albuginea oculi, a highly vascularized tissue. Our model's focus on the relevant traits present in the tunica albuginea oculi was strengthened by employing a strong image segmentation technique to separate the tunica albuginea oculi region from the entire eye image. Following segmentation, we classified the tunica albuginea oculi images as healthy or PCOS using a pre-trained deep learning model called Squeeze-and-Excitation Networks (SENet). In terms of prediction, the suggested system performed quite well.